Systems and methods for using backscatter imaging in precision agriculture

Abstract

Systems and methods for determining a mass of a crop by using at least one X-ray scanner is provided. The method includes obtaining at least two scan images of the crop, where a first of the at least two images is obtained along a first plane relative to the crop and a second of the at least two images is obtained along a second plane relative to the crop, and where the first plane is angularly displaced relative to the second plane, registering the first image and the second image, correcting the registered first and second images, and determining the mass of the crop from the corrected first and second images.

We claim: 
     
       1. A method for estimating weight of crop, wherein the crop comprises at least one row of plants and wherein the at least one row of plants comprises at least one vine and/or branch bearing fruit, the method comprising:
 irradiating a predefined area of the crop with X-rays from at least two sides; 
 obtaining scan images of the at least one row of plants; 
 performing contrast enhancement and de-noising with respect to each of the collected scan images; 
 performing a global registration of all the contrast enhanced, de-noised images; 
 obtaining split images representing individual vines and/or branches by separating vines and/or branches from said images; 
 performing a local registration of the obtained split images; 
 performing a cluster segmentation function on each of the split images; 
 processing the resultant segmented images using distance calibration; and, 
 estimating a weight of the crop by using the distance calibrated images. 
 
     
     
       2. The method of  claim 1 , wherein the step of collecting scan image data of at least one row of plants comprises flipping scan images, generated by irradiating the predefined area of the crop with X-rays, in a same predefined direction. 
     
     
       3. The method of  claim 1 , wherein separating vines and/or branches from said images comprises cutting out separate vines and/or branches from said images by discarding edges of at least one vine and/or branch bearing fruit in the at least one row of plants. 
     
     
       4. The method of  claim 1  wherein performing local registration comprises obtaining alignment between pairs of images showing different views of a same vine and/or branch. 
     
     
       5. The method of  claim 1  further comprising predicting a yield of the crop using the distance calibrated images. 
     
     
       6. The method of  claim 1  wherein obtaining scan images of at least one row of plants comprises:
 extracting image data from a raw data file; 
 creating a schematic map of each predefined area; 
 plotting a movement of a vehicle carrying a scanning apparatus being used for irradiating the crop with X-rays on the schematic map; and 
 determining a GPS coordinate of a point on the schematic map by correlating at least one timestamp of one or more GPS coordinates with at least one timestamp of when points on the schematic map were captured. 
 
     
     
       7. The method of  claim 6  further comprising locating rows of plants along with corresponding direction based on a direction of movement of the vehicle and flipping the located rows of plants in a predefined direction for obtaining a consistent sequence of plants in a row in each obtained scan image. 
     
     
       8. The method of  claim 6  further comprising normalizing each obtained scan image by using a predefined normalization bar. 
     
     
       9. The method of  claim 6  further comprising scanning GPS coordinates of each predefined area for obtaining distance between rows of plants in said areas. 
     
     
       10. The method of  claim 1  further comprising identifying and annotating the segmented images. 
     
     
       11. The method of  claim 1 , further comprising determining a cluster processing technique for processing each of the split images. 
     
     
       12. The method of  claim 1  further comprising processing the split images by using a coarse cluster segmentation method. 
     
     
       13. The method of  claim 1 , wherein the cluster segmentation function is either a classical cluster segmentation function or a deep learning cluster segmentation function. 
     
     
       14. The method of  claim 1  wherein an estimated weight of fruit hanging from plants is determined by determining a change in an X-ray signal backscattered by the fruit over a predefined period of time. 
     
     
       15. The method of  claim 14  wherein the fruit comprises one of: grapes, berries, citrus fruits, apples, melons, and tomatoes. 
     
     
       16. The method of  claim 14  wherein the X-ray signal backscattered from the fruit is proportional to a mass of the fruit and a distance of the fruit from a scanning system generating the X-rays for irradiating the fruit. 
     
     
       17. The method of  claim 16  wherein the X-ray signal backscattered from the fruit is proportional to the square of the distance of the fruit from the scanning system. 
     
     
       18. The method of  claim 16  wherein a total mass of the fruit is determined by integrating a signal intensity of the X-ray signal backscattered from the fruit across the crop. 
     
     
       19. The method of  claim 14  further comprising performing dual view data acquisition by scanning the fruit using two X-ray scanners simultaneously. 
     
     
       20. The method of  claim 14  further comprising performing dual view data acquisition by scanning the fruit using a single X-ray scanner with multiple acquisitions. 
     
     
       21. The method of  claim 14  wherein X-ray scanners are positioned outside of a fruiting region of a field, the scanners being positioned on opposite sides of a row of fruit plants. 
     
     
       22. The method of  claim 14  further comprising collecting images of the fruit and analyzing said images by using a distance normalization process at a pixel or feature level. 
     
     
       23. A method for determining a mass of a crop by using at least one X-ray scanner, the method comprising:
 obtaining at least two scan images of the crop, wherein a first of the at least two scan images is obtained along a first plane relative to the crop and a second of the at least two scan images is obtained along a second plane relative to the crop, and wherein the first plane is angularly displaced relative to the second plane; 
 registering the first scan image and the second scan image; 
 correcting the registered first and second scan images; and 
 determining the mass of the crop from the corrected first and second scan images. 
 
     
     
       24. The method of  claim 23  wherein the first plane is angularly displaced relative to the second plane by an angle ranging between 90 degrees and 270 degrees. 
     
     
       25. The method of  claim 23  wherein the first plane and the second plane are parallel to each other. 
     
     
       26. The method of  claim 23  wherein registering the first scan image and the second scan image comprises matching the first scan image and the second scan image by flipping and translating at least one of the first scan image and the second scan image relative to the other. 
     
     
       27. The method of  claim 23  wherein obtaining at least two scan images of the crop comprises scanning the crop using two X-ray scanners simultaneously. 
     
     
       28. The method of  claim 23  wherein obtaining at least two scan images of the crop comprises scanning the crop using a single X-ray scanner and executing multiple scans. 
     
     
       29. The method of  claim 23  wherein correcting the registered first scan images and second scan image comprises correcting said scan images for a plurality of predefined parameters. 
     
     
       30. The method of  claim 23  wherein correcting the registered first scan images and second scan images comprises correcting said scan images for one or more of contrast, brightness, intensity, or scale. 
     
     
       31. The method of  claim 23  wherein determining the mass of the crop from the corrected first and second scan images comprises identifying one or more clusters of fruit in the scan images and analyzing an intensity of the clusters on a pixel by pixel basis. 
     
     
       32. The method of  claim 31  further comprising summing and correlating the analyzed intensity of the clusters over a predefined period of time. 
     
     
       33. A system for determining a mass of a crop comprising:
 at least one X-ray scanner for obtaining at least two scan images of the crop, wherein a first of the at least two scan images is obtained along a first plane relative to the crop and a second of the at least two scan images is obtained along a second plane relative to the crop, and wherein the first plane is angularly displaced relative to the second plane; and 
 a controller coupled with the X-ray scanner, wherein the controller is adapted to:
 register the first and second images; 
 correct the registered first and second images; and 
 determine the mass of the crop from the corrected first and second scan images. 
 
 
     
     
       34. The system of  claim 33  wherein the first plane is angularly displaced relative to the second plane by an angle ranging between 90 degrees and 270 degrees. 
     
     
       35. The system of  claim 33  wherein the first plane and the second plane are parallel to each other. 
     
     
       36. The system of  claim 33  wherein registering the first scan image and the second scan image comprises matching the first image and the second image by flipping and translating at least one of the first image and the second image relative to the other. 
     
     
       37. The system of  claim 33  comprising two X-ray scanners for obtaining the at least two scan images of the crop simultaneously. 
     
     
       38. The system of  claim 33  wherein the at least one X-ray scanner is used to scan the crop at least two times to obtain the at least two scan images of the crop. 
     
     
       39. The system of  claim 33  wherein correcting the registered first and second scan images comprises correcting said images for a plurality of predefined parameters. 
     
     
       40. The system of  claim 33  wherein correcting the registered first and second scan images comprises correcting said images for one or more of contrast, brightness, intensity, or scale. 
     
     
       41. The system of  claim 33  wherein determining the mass of the crop from the corrected first and second scan images comprises identifying one or more clusters of fruit in the images and analyzing an intensity of the clusters on a pixel by pixel basis. 
     
     
       42. The system of  claim 33  further comprising summing and correlating the analyzed intensity of the clusters over a predefined period of time. 
     
     
       43. A system for estimating a weight of crop, wherein the crop comprises at least one row of plants and wherein the at least one row of plants comprises vines and/or branches bearing fruit, the system comprising:
 at least one X-ray scanner for irradiating a predefined area of the crop with X-rays from at least two sides; and 
 a controller coupled with the at least one X-ray scanner, wherein the controller is adapted to:
 obtain scan images of the at least one row of plants; 
 perform contrast enhancement and de-noising with respect to each of the collected scan images; 
 perform a global registration of the contrast enhanced, de-noised images; 
 obtain split images by separating vines and/or branches from said images; 
 perform a local registration of the obtained split images; 
 perform a cluster segmentation function on a predefined group of the split images; 
 process the segmented images using distance calibration; and 
 estimate a weight of the crop by using the distance calibrated images. 
 
 
     
     
       44. The system of  claim 43 , wherein collecting scan image data of at least one row of plants comprises flipping scan images, generated by irradiating the predefined area of the crop with X-rays, in a same predefined direction. 
     
     
       45. The system of  claim 43 , wherein obtaining split images comprises cutting out separate vines and/or branches from said images by discarding edges of the vines and/or branches from the images. 
     
     
       46. The system of  claim 43  wherein performing local registration comprises obtaining alignment between pairs of images showing different views of a same plant. 
     
     
       47. The system of  claim 43  being used for predicting a yield of the crop using the distance calibrated images. 
     
     
       48. The system of  claim 43  wherein obtaining scan images of at least one row of plants comprises:
 extracting image data from a raw data file; 
 creating a schematic map of each predefined area; 
 plotting a movement of a vehicle carrying a scanning apparatus being used for irradiating the crop with X-rays on the schematic map; and 
 determining a GPS coordinate of a point on the schematic map by correlating at least one timestamp of one or more GPS coordinates with at least one timestamp of when points on the schematic map were captured. 
 
     
     
       49. The system of  claim 43  wherein the controller locates rows of plants along with corresponding direction based on a direction of movement of the vehicle; and flips all the located rows of plant in a predefined direction for obtaining a consistent sequence of plants in a row in each obtained scan image. 
     
     
       50. The system of  claim 43  wherein the controller normalizes each obtained scan image by using a predefined normalization bar. 
     
     
       51. The system of  claim 43  wherein the controller directs the X-ray scanner to scan GPS coordinates of each predefined area for obtaining distance between rows of plants in said areas. 
     
     
       52. The system of  claim 43  wherein the controller identifies and annotates the segmented images. 
     
     
       53. The system of  claim 43  wherein the controller processes the split images by using a coarse cluster segmentation method. 
     
     
       54. The system of  claim 43 , wherein the controller performs the cluster segmentation function as either a classical cluster segmentation function or a deep learning cluster segmentation function. 
     
     
       55. The method of  claim 43 , wherein the controller determines a cluster processing technique for processing each of the split images. 
     
     
       56. The system of  claim 43  wherein the controller determines weight of fruit hanging from plants by determining a change in an X-ray signal backscattered by the fruit over a predefined period of time. 
     
     
       57. The system of  claim 43  wherein the fruit comprises one of: grapes, berries, citrus fruits, apples, melons, and tomatoes. 
     
     
       58. The system of  claim 43  wherein the X-ray signal backscattered from the fruit is proportional to a mass of the fruit and a distance of the fruit from a scanning system generating the X-rays for irradiating the fruit. 
     
     
       59. The system of  claim 57  wherein the X-ray signal backscattered from the fruit is proportional to the square of the distance of the fruit from the scanning system. 
     
     
       60. The system of  claim 43  wherein a total mass of the fruit is determined by integrating a signal intensity of X-ray signal backscattered from the fruit across the crop.